Saved in:
Bibliographic Details
Main Authors: Haojie, Liu, Suixiang, Gao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.16709
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915571033964544
author Haojie, Liu
Suixiang, Gao
author_facet Haojie, Liu
Suixiang, Gao
contents We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM performs efficient single-step generation by learning a self-consistent mapping between noisy and clean motion states. The framework adopts a Transformer-based spatiotemporal architecture with temporal embeddings to model long-range dependencies and preserve motion coherence. Experiments on Human3.6M and HumanEva-I demonstrate that HumanCM achieves comparable or superior accuracy to state-of-the-art diffusion models while reducing inference steps by up to two orders of magnitude.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16709
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HumanCM: One Step Human Motion Prediction
Haojie, Liu
Suixiang, Gao
Computer Vision and Pattern Recognition
Artificial Intelligence
We present HumanCM, a one-step human motion prediction framework built upon consistency models. Instead of relying on multi-step denoising as in diffusion-based methods, HumanCM performs efficient single-step generation by learning a self-consistent mapping between noisy and clean motion states. The framework adopts a Transformer-based spatiotemporal architecture with temporal embeddings to model long-range dependencies and preserve motion coherence. Experiments on Human3.6M and HumanEva-I demonstrate that HumanCM achieves comparable or superior accuracy to state-of-the-art diffusion models while reducing inference steps by up to two orders of magnitude.
title HumanCM: One Step Human Motion Prediction
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2510.16709